***Please note the change of date from previous message
LANCASTER POSTGRADUATE STATISTICS CENTRE - MASTER CLASS
May 12th - 14th, 2008
Linear and smooth modelling of location, scale, skewness and kurtosis for a wide class of distributions: a short course on GAMLSS using R.
Course tutors: Bob Rigby and Mikis Stasinopoulos
What is GAMLSS?
Generalized Additive Models for Location, Scale and Shape (GAMLSS) were introduced by Rigby and Stasinopoulos (2005). GAMLSS is a very general framework for univariate regression type statistical problems. In GAMLSS the exponential family distribution assumption used in Generalized Linear Model (GLM) and Generalized Additive Model (GAM), (see Nelder and Wedderburn, 1972 and Hastie and Tibshirani, 1990, respectively) is relaxed and replaced by a very general distribution family including highly skew and kurtotic discrete and continuous distributions. The systematic part of the model is expanded to allow modelling not only the mean (or location) but other parameters of the distribution of y as linear parametric, non-linear parametric or additive non-parametric functions of explanatory variables and/or random effects terms. Maximum (penalized) likelihood estimation is used to fit the models. The algorithms used to fit the model are described in detail in Rigby and Stasinopoulos (2005). For medium to large size data, GAMLSS allow flexibility in univariate statistical modelling far beyond other currently available methods. The most important application of GAMLSS up to now is its use by the Department of Nutrition for Health and Development of the World Health Organization to construct centiles for worldwide standard growth curves. The range of possible applications for GAMLSS though is a lot more general and examples will be given of its usefulness in modelling medical, social and economic data. More recent work, for example mixture distributions, the inclusion of non linear parameter components as additive terms, the inclusion of truncated distributions and censored data within GAMLSS, will be also discussed.
For more information about GAMLSS visit http://www.gamlss.com/
Details of the course
The short course will give an overview of GAMLSS and how to use the flexibility of the framework to deal with practical applications. GAMLSS is implemented in a series of packages in R and the course contains practical sessions to familiarized users with those packages. The course is designed for applied statisticians and PhD students in the field of social statistics, biostatistics, medical statistics and other related fields, where the data requires modelling the response variable using a flexible distribution.
The cost of this masterclass is £120 for 3 days which includes lunch, teas and coffee, together with a presentation pack and course notes.
Accommodation is not included - for accommodation options (including campus accommodation) please visit http://www.maths.lancs.ac.uk/department/info/about/visitors/ .
Lectures and hands-on practical sessions for the first two and a half days will be complemented with a half day mentoring session using participants' datasets on the last day.
To register and pay for a place on the course please go to http://psc.maths.lancs.ac.uk/shortCourses/
There are a limited number of places available so early booking is advised. The closing date for application is Friday 25th April 2008
|